The Multiscale Deep Neural Networks: Unveiling New Directions in Text Sentiment Analysis

Hongyu Hu; Jie Zhang; Yang Sun

doi:10.61187/ita.v2i2.65

Authors

Hongyu Hu
huhongyu525@163.com
Mental Health Center, Wuhan Donghu University, No.301 Wenhua Street, 430200, Wuhan, Hubei, China
Jie Zhang College of Medicine and Biological Information Engineering, Northeastern University, No.500 Wisdom Street, 110169, Shenyang, Liaoning, China
Yang Sun College of Life Sciences, Shandong Normal University, No.88 Wenhua East Road, 250014, Jinan, Shandong, China

Keywords:

textual data, sentiment analysis, deep learning, multiscale feature, term frequency-inverse document frequency

Abstract

The rapid proliferation of textual data across online platforms necessitates accurate sentiment analysis. Traditional sentiment analysis methods, which are based on lexical ontology theories and basic rules, have shown limitations in capturing the subtleties and contextual nuances of language. Recent advancements in machine learning and deep learning have shifted the focus toward model-based approaches, yet they often overlook distinct emotional dimensions in varying text structures. To address this issue, we introduce a novel deep neural network architecture that employs multiscale feature extraction and is designed to capture a broad series of emotional features within texts. This approach significantly improves the accuracy of sentiment analysis by effectively discerning subtle emotional nuances. We validate the effectiveness of our proposed model through extensive experiments and comparisons with benchmark methods, demonstrating its superiority in sentiment analysis tasks. Additionally, a detailed ablation study highlights the impact of the multiscale module on the model’s performance.

Downloads

Download data is not yet available.

References

Zad, S., Heidari, M., Jones, J.H., et al. A survey on concept-level sentiment analysis techniques of textual data. In proceedings of 2021 IEEE World AI IoT Congress (AIIoT), 2021, 0285–0291. https://doi.org/1010.1109/AIIoT52608.2021.9454169

Ullah, M.A., Marium, S.M., Begum, S.A.,et al. An algorithm and method for sentiment analysis using the text and emoticon. ICT Express, 2020, 6(4), 357–360. https://doi.org/10.1016/j.icte.2020.07.003

Saura, J.R., Palos-Sanchez, P., Grilo, A. Detecting indicators for startup business success: Sentiment analysis using text data mining. Sustainability, 2019, 11(3), 917. https://doi.org/10.3390/su11030917

Mouthami, K., Devi, K.N., Bhaskaran, V.M. Sentiment analysis and classification based on textual reviews. In proceedings of 2013 International Conference on Information Communication and Embedded Systems (ICICES), 2013, 271–276. https://doi.org/1010.1109/ICICES.2013.6508366

Kauffmann, E., Peral, J., Gil, D., et al. Managing marketing decision-making with sentiment analysis: An evaluation of the main product features using text data mining. Sustainability, 2019, 11(15), 4235. https://doi.org/10.3390/su11154235

Pradha, S., Halgamuge, M.N., Vinh, N.T.Q. Effective text data preprocessing technique for sentiment analysis in social media data. In proceedings of 2019 11th International Conference on Knowledge and Systems Engineering (KSE), 2019, 1–8. https://doi.org/1010.1109/KSE.2019.8919368

Hu, R., Rui, L., Zeng, P., et al. Text sentiment analysis: A review. In proceedings of 2018 IEEE 4th International Conference on Computer and Communications (ICCC),2018, 2283–2288. https://doi.org/1010.1109/CompComm.2018.8780909

Mehta, P., Pandya, S. A review on sentiment analysis methodologies, practices and applications. International Journal of Scientific and Technology Research, 2020, 9(2), 601–609.

Ali, F., Kwak, D., Khan, P., et al. Transportation sentiment analysis using word embedding and ontologybased topic modeling. Knowledge-Based Systems, 2019, 174, 27–42. https://doi.org/10.1016/j.knosys.2019.02.033

Zhuang, L., Schouten, K., Frasincar, F. Soba: Semi-automated ontology builder for aspect-based sentiment analysis. Journal of Web Semantics, 2020, 60, 100544. https://doi.org/10.1016/j.websem.2019.100544

Colace, F., De Santo, M., Greco, L., et al. Probabilistic approaches for sentiment analysis: Latent dirichlet allocation for on-tology building and sentiment extraction. Sentiment Analysis and Ontology Engineering: An Environment of Computational Intelligence, 2016, 75–91. https://doi.org/10.1007/978-3-319-30319-2_4

Meškelė, D., Frasincar, F. Aldonar. A hybrid solution for sentence-level aspectbased sentiment analysis using a lexicalized domain ontology and a regularized neural attention model. Information Processing & Management, 2020, 57(3), 102211. https://doi.org/10.1016/j.ipm.2020.102211

Kontopoulos, E., Berberidis, C., Dergiades, T., et al. Ontology-based sentiment analysis of twitter posts. Expert systems with applications, 2013, 40(10), 4065–4074. https://doi.org/10.1016/j.eswa.2013.01.001

Dragoni, M., Poria, S., Cambria, E. Ontosenticnet: A commonsense ontology for sentiment analysis. IEEE Intelligent Systems 2018, 33(3), 77–85. https://doi.org/1010.1109/MIS.2018.033001419

Neethu, M., Rajasree, R. Sentiment analysis in twitter using machine learning techniques. In proceedings of 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT), 2013, 1–5. https://doi.org/1010.1109/ICCCNT.2013.6726818

Agarwal, B., Mittal, N., Agarwal, B., et al. Machine learning approach for sentiment analysis. Prominent feature extraction for sentiment analysis, 2016, 21–45. https://doi.org/10.1007/978-3-319-25343-5_3

Hasan, A., Moin, S., Karim, A., et al. Machine learning-based sentiment analysis for twitter accounts. Mathematical and computational applications, 2018, 23(1), 11. https://doi.org/10.3390/mca23010011

Rhanoui, M., Mikram, M., Yousfi, S., Barzali, S.: A cnn-bilstm model for document-level sentiment analysis. Machine Learning and Knowledge Extraction, 2019, 1(3), 832–847. https://doi.org/10.3390/make1030048

Agarwal, A., Yadav, A., Vishwakarma, D.K. Multimodal sentiment analysis via rnn variants. In proceedings of 2019 IEEE International Conference on Big Data, Cloud Computing, Data Science & Engineering (BCD), 2019, 19–23. https://doi.org10.1109/BCD.2019.8885108

Maas, A., Daly, R.E., Pham, P.T., et al. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011, 142–150.

Poria, S., Cambria, E., Winterstein, G., et al. Sentic patterns: Dependency-based rules for concept-level sentiment analysis. Knowledge-Based Systems, 2014, 69, 45–63. https://doi.org/10.1016/j.knosys.2014.05.005

Di Caro, L., Grella, M. Sentiment analysis via dependency parsing. Computer Standards & Interfaces, 2013, 35(5), 442–453. https://doi.org/10.1016/j.csi.2012.10.005

Gajendrasinh, R.D., Bohara, M.H. Sentiment analysis for feature extraction using dependency tree and named entities. In proceedings of International Conference on Innovations in Information Embedded and Communication Systems (ICIIECS), 2017, 587–592.

Nakagawa, T., Inui, K., Kurohashi, S. Dependency tree-based sentiment classification using crfs with hidden variables. In proceedings of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Associ-ation for Computational Linguistics, 2010, 786–794.

Hardeniya, T., Borikar, D.A. Dictionary based approach to sentiment analysis-a review. International Journal of Advanced Engineering, Management and Science, 2016, 2(5), 239438.

Pandey, S., Sagnika, S., Mishra, B.S.P. A technique to handle negation in sentiment analysis on movie reviews. In proceedings of 2018 International Conference on Communication and Signal Processing (ICCSP), 2018, 737–743. https://doi.org/10.1109/ICCSP.2018.8524421